OpenCodePapers

unsupervised-semantic-segmentation-with-8

Semantic SegmentationUnsupervised Semantic SegmentationUnsupervised Semantic Segmentation with Language-image Pre-training
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodemIoUModelNameReleaseDate
CorrCLIP: Reconstructing Correlations in CLIP with Off-the-Shelf Foundation Models for Open-Vocabulary Semantic Segmentation✓ Link50.8CorrCLIP2024-11-15
TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models✓ Link46.1TextRegion2025-05-29
Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation✓ Link44.3Trident2024-11-14
ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation✓ Link39.6ProxyCLIP2024-08-09
TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification✓ Link37.6TagAlign2023-12-21
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias✓ Link37.4TTD (TCL)2024-03-30
Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs✓ Link33.9TCL2022-12-01
COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training✓ Link33.7COSMOS ViT-B/162024-12-02
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias✓ Link31.0TTD (MaskCLIP)2024-03-30
Extract Free Dense Labels from CLIP✓ Link26.4MaskCLIP2021-12-02
GroupViT: Semantic Segmentation Emerges from Text Supervision✓ Link23.4GroupViT (RedCaps)2022-02-22
ReCo: Retrieve and Co-segment for Zero-shot Transfer✓ Link22.3ReCo2022-06-14
Check out how to contribute new results.